Limits...
Inter-species prediction of protein phosphorylation in the sbv IMPROVER species translation challenge.

Biehl M, Sadowski P, Bhanot G, Bilal E, Dayarian A, Meyer P, Norel R, Rhrissorrakrai K, Zeller MD, Hormoz S - Bioinformatics (2014)

Bottom Line: In addition, post hoc analyses of the datasets and challenge results were performed by the participants and challenge organizers.The challenge outcome indicates that successful prediction of protein phosphorylation status in human based on rat phosphorylation levels is feasible.However, within the limitations of the computational tools used, the inclusion of gene expression data does not improve the prediction quality.

View Article: PubMed Central - PubMed

Affiliation: Johann Bernoulli Institute for Mathematics and Computer Science, University of Groningen, 9700 AK Groningen, The Netherlands, University of California, Irvine, CA 92617, Department of Physics and Department of Molecular Biology and Biochemistry, Busch Campus, Rutgers University, Piscataway, NJ 08854, IBM T.J. Watson Research Center, Computational Biology, Yorktown Heights, NY 10598, Kavli Institute for Theoretical Physics, University of California, Santa Barbara, CA 93106, USA.

Show MeSH
Schematic illustration of the sub-challenge structure and datasets. The objective was to predict the phosphorylation status (P) of human phosphoproteins to stimuli subset B, shown in red, given the gene expression (GEx) and phosphorylation data for rat under the same stimuli. Available data (blue) also comprised the measurements of phosphorylation and gene expression in rat and human under a different set of stimuli A, which served as the training data. Human GEx data under the set of stimuli B was unavailable (shown in gray)
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4325536&req=5

btu407-F1: Schematic illustration of the sub-challenge structure and datasets. The objective was to predict the phosphorylation status (P) of human phosphoproteins to stimuli subset B, shown in red, given the gene expression (GEx) and phosphorylation data for rat under the same stimuli. Available data (blue) also comprised the measurements of phosphorylation and gene expression in rat and human under a different set of stimuli A, which served as the training data. Human GEx data under the set of stimuli B was unavailable (shown in gray)

Mentions: Figure 1 illustrates the challenge setup and structure of the datasets. Each panel of data labeled as ‘P’ corresponds to the phosphorylation levels of 16 different proteins under 26 chemical stimuli in dataset (A) and 26 different stimuli in dataset (B). Phosphorylation measurements, using the Luminex xMap (TM) platform, were performed at 5 and 25 min after exposure to the stimuli. Repeated measurements provided two or three replicates per stimulus and protein. In addition, five or six DME (Dulbecco’s modified Eagle’s Medium) control measurements in absence of any stimulus were provided.Fig. 1.


Inter-species prediction of protein phosphorylation in the sbv IMPROVER species translation challenge.

Biehl M, Sadowski P, Bhanot G, Bilal E, Dayarian A, Meyer P, Norel R, Rhrissorrakrai K, Zeller MD, Hormoz S - Bioinformatics (2014)

Schematic illustration of the sub-challenge structure and datasets. The objective was to predict the phosphorylation status (P) of human phosphoproteins to stimuli subset B, shown in red, given the gene expression (GEx) and phosphorylation data for rat under the same stimuli. Available data (blue) also comprised the measurements of phosphorylation and gene expression in rat and human under a different set of stimuli A, which served as the training data. Human GEx data under the set of stimuli B was unavailable (shown in gray)
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4325536&req=5

btu407-F1: Schematic illustration of the sub-challenge structure and datasets. The objective was to predict the phosphorylation status (P) of human phosphoproteins to stimuli subset B, shown in red, given the gene expression (GEx) and phosphorylation data for rat under the same stimuli. Available data (blue) also comprised the measurements of phosphorylation and gene expression in rat and human under a different set of stimuli A, which served as the training data. Human GEx data under the set of stimuli B was unavailable (shown in gray)
Mentions: Figure 1 illustrates the challenge setup and structure of the datasets. Each panel of data labeled as ‘P’ corresponds to the phosphorylation levels of 16 different proteins under 26 chemical stimuli in dataset (A) and 26 different stimuli in dataset (B). Phosphorylation measurements, using the Luminex xMap (TM) platform, were performed at 5 and 25 min after exposure to the stimuli. Repeated measurements provided two or three replicates per stimulus and protein. In addition, five or six DME (Dulbecco’s modified Eagle’s Medium) control measurements in absence of any stimulus were provided.Fig. 1.

Bottom Line: In addition, post hoc analyses of the datasets and challenge results were performed by the participants and challenge organizers.The challenge outcome indicates that successful prediction of protein phosphorylation status in human based on rat phosphorylation levels is feasible.However, within the limitations of the computational tools used, the inclusion of gene expression data does not improve the prediction quality.

View Article: PubMed Central - PubMed

Affiliation: Johann Bernoulli Institute for Mathematics and Computer Science, University of Groningen, 9700 AK Groningen, The Netherlands, University of California, Irvine, CA 92617, Department of Physics and Department of Molecular Biology and Biochemistry, Busch Campus, Rutgers University, Piscataway, NJ 08854, IBM T.J. Watson Research Center, Computational Biology, Yorktown Heights, NY 10598, Kavli Institute for Theoretical Physics, University of California, Santa Barbara, CA 93106, USA.

Show MeSH